New Economics Papers
on Computational Economics
Issue of 2007‒03‒10
eight papers chosen by

  1. A neural network architecture for data editing in the Bank of Italy’s business surveys By Claudia Biancotti; Leandro D'Aurizio; Raffaele Tartaglia-Polcini
  2. Boosting Estimation of RBF Neural Networks for Dependent Data By George Kapetanios; Andrew P. Blake
  3. Completing correlation matrices of arbitrary order by differential evolution method of global optimization: A Fortran program By Mishra, SK
  4. INDOTERM, a multiregional model of Indonesia By Mark Horridge; Glyn Wittwer
  5. Constructing Indonesian Social Accounting Matrix for Distributional Analysis in the CGE Modelling Framework By Arief Anshory Yusuf
  7. Water price and water reallocation in Andalusia. A computable general equilibrium approach By Esther Velázquez; M. Alejandro Cardenete; Geoffrey J.D. Hewings
  8. Optimization in a Simulation Setting: Use of Function Approximation in Debt Strategy Analysis By David Jamieson Bolder; Tiago Rubin

  1. By: Claudia Biancotti (Bank of Italy); Leandro D'Aurizio (Bank of Italy); Raffaele Tartaglia-Polcini (Bank of Italy)
    Abstract: This paper presents an application of neural network models to predictive classification for data quality control. Our aim is to identify data affected by measurement error in the Bank of Italy’s business surveys. We build an architecture consisting of three feed-forward networks for variables related to employment, sales and investment respectively: the networks are trained on input matrices extracted from the error-free final survey database for the 2003 wave, and subjected to stochastic transformations reproducing known error patterns. A binary indicator of unit perturbation is used as the output variable. The networks are trained with the Resilient Propagation learning algorithm. On the training and validation sets, correct predictions occur in about 90 per cent of the records for employment, 94 per cent for sales, and 75 per cent for investment. On independent test sets, the respective quotas average 92, 80 and 70 per cent. On our data, neural networks perform much better as classifiers than logistic regression, one of the most popular competing methods, on our data. They appear to provide a valid means of improving the efficiency of the quality control process and, ultimately, the reliability of survey data.
    Keywords: data quality, data editing, binary classification, neural networks, measurement error
    JEL: C42 C45
  2. By: George Kapetanios (Queen Mary, University of London); Andrew P. Blake (Bank of England)
    Abstract: This paper develops theoretical results for the estimation of radial basis function neural network specifications, for dependent data, that do not require iterative estimation techniques. Use of the properties of regression based boosting algorithms is made. Both consistency and rate results are derived. An application to nonparametric specification testing illustrates the usefulness of the results.
    Keywords: Neural Networks, Boosting
    JEL: C12 C13 C22
    Date: 2007–03
  3. By: Mishra, SK
    Abstract: Correlation matrices have many applications, particularly in marketing and financial economics. The need to forecast demand for a group of products in order to realize savings by properly managing inventories requires the use of correlation matrices. In many cases, due to paucity of data/information or dynamic nature of the problem at hand, it is not possible to obtain a complete correlation matrix. Some elements of the matrix are unknown. Several methods exist that obtain valid complete correlation matrices from incomplete correlation matrices. In view of non-unique solutions admissible to the problem of completing the correlation matrix, some authors have suggested numerical methods that provide ranges to different unknown elements. However, they are limited to very small matrices up to order 4. Our objective in this paper is to suggest a method (and provide a Fortran program) that completes a given incomplete correlation matrix of an arbitrary order. The method proposed here has an advantage over other algorithms due to its ability to present a scenario of valid correlation matrices that might be obtained from a given incomplete matrix of an arbitrary order. The analyst may choose some particular matrices, most suitable to his purpose, from among those output matrices. Further, unlike other methods, it has no restriction on the distribution of holes over the entire matrix, nor the analyst has to interactively feed elements of the matrix sequentially, which might be quite inconvenient for larger matrices. It is flexible and by merely choosing larger population size one might obtain a more exhaustive scenario of valid matrices.
    Keywords: Incomplete; complete; correlation matrix; valid; semi-definite; eigenvalues; Differential Evolution; global optimization; computer program; fortran; financial economics; arbitrary order
    JEL: G10 C88 C63 C61
    Date: 2007–03–05
  4. By: Mark Horridge (Monash University); Glyn Wittwer (Monash University)
    Abstract: INDOTERM , a member of the TERM family (TERM = The Enormous Regional Model), is a "bottom-up" CGE model of Indonesia which treats West Java and the rest of Indonesia as separate economies. The TERM approach was created specifically to deal with highly disaggregated regional data while providing a quick solution to simulations. This paper describes the technical detail of this model.
    Keywords: Computable General Equilibrium, Regional CGE, Indonesia
    JEL: D58
    Date: 2006–08
  5. By: Arief Anshory Yusuf (Department of Economics, Padjadjaran University)
    Abstract: The distributional impact of policies analyzed in the CGE modelling framework have been constrained in part by the absence of a Social Accounting Matrix (SAM) with disaggregated households. Since Indonesian official SAM does not distinguish households by income or expenditure size, it has prevented accurate assesment for the distributional impact, such as calculation of inequality or poverty incidence. This paper describes how the Indonesian SAM for the year 2003, with 181 industries, 181 commodities, and 200 households (100 urban and 100 rural households grouped by expenditure per capita centiles) was constructed. The SAM (with the size of 768x768 accounts) constitutes the the most disaggregated SAM for Indonesia at both the sectoral and household level. SAM Construction is an essential part of CGE modeling, and this documentation provides greater transparency as well as replicability for further improvement.
    Keywords: Social Accounting Matrix, Computable General Equilibrium, Indonesia
    JEL: D30 D58
    Date: 2006–11
  6. By: Patrice Gaubert (MATISSE - Modélisation Appliquée, Trajectoires Institutionnelles et Stratégies Socio-Économiques - [CNRS : UMR8595] - [Université Panthéon-Sorbonne - Paris I]); Marie Cottrell (MATISSE - Modélisation Appliquée, Trajectoires Institutionnelles et Stratégies Socio-Économiques - [CNRS : UMR8595] - [Université Panthéon-Sorbonne - Paris I], SAMOS - Statistique Appliquée et MOdélisation Stochastique - [Université Panthéon-Sorbonne - Paris I])
    Abstract: Using the Panel Study of Income Dynamics data on the period 1982-1992, this paper investigates some mechanisms of the labor market in the United States. This market is analyzed as a stable structure constituted of segments which present contrasted characteristics under the usual distinction between primary and secondary sectors. Using a neural network algorithm applied on quantitative variables measured at the level of heads of household, a broad classification in four classes of situations is constructed. It shows a clear hierarchy going from situations of very precarious work or no work at all, to situations of stable jobs with higher wages than the average. A Markov chain, constructed with the trajectories between the different situations of these workers, shows a very stable structure of this segmented labor market. Keywords: segmented labor market, unemployment, trajectories, Kohonen algorithm, Markov chain.
    Keywords: Keywords: segmented labor market, unemployment, trajectories, Kohonen algorithm, Markov chain.
    Date: 2007–02–28
  7. By: Esther Velázquez (Department of Economics, Universidad Pablo de Olavide); M. Alejandro Cardenete (Department of Economics, Universidad Pablo de Olavide); Geoffrey J.D. Hewings (Regional Economics Application Laboratory and University of Illinois)
    Abstract: The objective of this work is to analyze the effects that an increase in the price of the water delivered to the agriculture sector to promote the conservation of this resource would have on the efficiency of the consumption of water and the possible reallocation of water to the remaining productive sectors. The analysis is motivated by the fact that the agriculture consumes a disproportionately large amount of water at very low prices. The methodology that will be used to explore the implications on the economy will be a computable general equilibrium model (CGE), previously designed for an analysis of the direct taxes of the Andalusian economy (Cardenete and Sancho, 2003), but now enhanced and extended to include emissions of pollutants and the introduction of environmental taxes (André, Cardenete and Velázquez, 2005). This model has been further modified to introduce the variations in the water price that we will try to analyze by means of a tariff applied on the production structure. The main conclusion drawn indicates that, although the tax policy applied does not correspond to a significant water saving in the above-mentioned sector, a reallocation of this resource is achieved which seems to generate a more efficient and more rational behavior from a production point of view.
    Keywords: environmental tax reforms, computable general equilibrium, water price
    JEL: D58 H21 H22
    Date: 2007–03
  8. By: David Jamieson Bolder; Tiago Rubin
    Abstract: This paper provides an analysis of how a firm’s decision to serve a foreign market by exporting or by engaging in foreign direct investment (FDI) affects firm productivity, when productivity is endogeneous as a function of training. The main result of our paper is that, with endogeneous productivity, exporting results in lower productivity than does FDI, but exporting may result in higher or lower employment and output than does FDI. We also show that FDI has lower employment, higher training, higher wages and higher productivity than does production for the home market. A further interesting and unexpected result of our model is that exporting results in the same level of training and productivity as does production for the home market. However, under the same demand conditions, the exporting firm employs less labour for foreign production than for home production and, consequently, output for the foreign market is lower than output for the home market. In addition, we investigate the firm's decision to serve the foreign market by exporting or by engaging in FDI and determine parameter values for which either regime is chosen.
    Keywords: International topics; Labour markets; Productivity
    JEL: F22 F23
    Date: 2007

General information on the NEP project can be found at For comments please write to the director of NEP, Marco Novarese at <>. Put “NEP” in the subject, otherwise your mail may be rejected.
NEP’s infrastructure is sponsored by the School of Economics and Finance of Massey University in New Zealand.